© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7647
    Prev
    Next
    INDEX
    Explanations

    references to legal documents or cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numbered footnotes

    np_acts-logits-general · gemini-2.0-flash

    Appointed counsel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     offense
    -0.42
    Solved
    -0.41
    abestanden
    -0.40
    hards
    -0.38
    prises
    -0.38
    諜
    -0.38
    cris
    -0.38
     swallowed
    -0.38
     Juarez
    -0.37
    roll
    -0.37
    POSITIVE LOGITS
     esternos
    0.52
    лтамалар
    0.51
     Италијани
    0.50
    exels
    0.49
    RTEE
    0.49
    SharedCtor
    0.48
     Normdatei
    0.48
    $_['
    0.47
    Földrajzportál
    0.47
    {{/
    0.47
    Activations Density 0.584%

    No Known Activations